{"ID":2897373,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.04702","arxiv_id":"2507.04702","title":"Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning","abstract":"Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of information and redundancy than texts or images. Models should present comprehensive understanding of the whole video to accurately retrieve query-relevant clips. We thus propose Tempo-R0: a Video Multimodal Large Language Model (Video-MLLM) for the temporal video grounding task via multimodal temporal sensing reinforcement. Specifically, during the preprocessing stage of our pipeline, we employ Self-adaptive Attention Allocation (SAA) method based on frame content variation to efficiently use the MLLM's limited attention. The Explicit Timestamp-modal Aligned (ETA) method is also utilized to strengthen our model's capability to perceive the boundaries of events in the video. In the fine-tuning part of our pipeline, we creatively apply Partial Irrelevance Refusing-based Group Relative Policy Optimization (PIR-GRPO) in TVG area to foster model's temporal reasoning from not only accepting relevant video-query pairs but also refusing irrelevant ones. Experiments demonstrate that our method accomplishes a notable advantage over SOTA solutions by around 3.5% on both the original QVHighlights testbench and its corrected version with more reasonable ground truth annotations.","short_abstract":"Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of information and redundancy than texts or images. Models should present comprehensi...","url_abs":"https://arxiv.org/abs/2507.04702","url_pdf":"https://arxiv.org/pdf/2507.04702v1","authors":"[\"Feng Yue\",\"Zhaoxing Zhang\",\"Junming Jiao\",\"Zhengyu Liang\",\"Shiwen Cao\",\"Feifei Zhang\",\"Rong Shen\"]","published":"2025-07-07T06:51:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}